SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.05967 · NeurIPS · 2021

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations

Stamatios Georgoulis, K Leuven, Wouter Van Gansbeke, Simon Vandenhende, Luc Gool, / Cvl

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existing methods. Our results show that an approach like MoCo [22] works surprisingly well across: (i) object-versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets. Second, given the generality of the approach, we try to realize further gains with minor modifications. We show that learning additional invariances -through the use of multi-scale cropping, stronger augmentations and nearest neighbors -improves the representations. Finally, we observe that MoCo learns spatially structured representations when trained with a multi-crop strategy. The representations can be used for semantic segment retrieval and video instance segmentation without finetuning. Moreover, the results are on par with specialized models. We hope this work will serve as a useful study for other researchers. The code and models are available 2 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.05967")
get_code_for_paper("2106.05967")
have("2106.05967")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.05967.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.05967.svg)](https://syntology.ai/paper/2106.05967)

Connect an agent — have() is free.